School of Engineering Department of Computer Science and Engineering 89 AI meets Big Data: User Analytics and Personalized Recommendation Based on Location Data Supervisor: CHAN, Gary Shueng Han / CSE Student: MOHAMMAD-SUFIAN / COSC Course: UROP1100, Spring Indoor localisation is a hot topic in the field of big data and machine learning, which aims to utilise crowdsourced Received Signal Strength Indicator (RSSI) data collected from multiple reference access points (AP) propagating some variation of wave signal. This report addresses how attempts were made to utilise the power of well-studied convolutional neural networks (CNNs) in order to experiment with their methodologies and see if they could be applied to indoor localisation tasks using user location data in the form of these RSSI fingerprints. With the help of some state-of-the-art analytical tools, this report will demonstrate that there is potential for CNNs to play successful roles in indoor localisation tasks. AI meets Big Data: User Analytics and Personalized Recommendation Based on Location Data Supervisor: CHAN, Gary Shueng Han / CSE Student: SHE, Fong Wing / RMBI Course: UROP1100, Fall In this pandemic time, health becomes one of the most important concerns of people around the world. A medical system that could enable efficient communication between patients, health professionals, nurses, etc., and monitoring of health conditions could help improve the healthcare system and prevent diseases. This project therefore aims to develop a Flutter application for health management and it is still in progress. In summary, 5 tasks have been performed, which includes investigating the methods for collecting bluetooth/IoT data from Android, reviewing 2 medical research papers, learning the basics of Flutter through a trial project, implementing the layouts of 2 screens, and setting up a local push notification for the healthcare manager application. AI meets Big Data: User Analytics and Personalized Recommendation Based on Location Data Supervisor: CHAN, Gary Shueng Han / CSE Student: WANG, Zekai / CPEG Course: UROP1000, Summer Indoor localization has been under research since we spend more time using our mobile devices inside huge building complexes with multiple floors. Industry and academia have introduced different approaches, they vary in their input data. For example, some use ultrawideband (UWB), Bluetooth signal or device built-in accelerometer as the input data for localization. This report will focus on using WIFI fingerprints to estimate the user’s location by applying machine learning technique inside an MTR station. The result of this method is, unfortunately, unsatisfactory from the real application point of view because of the sparse accessing point. However, it is believed that the key to improving the accuracy of our estimation is how to process the input data correctly, especially when the training data is limited in size. Therefore, another focus of this report is to analyze different dimensional reduction / feature extraction algorithms applying onto the input data, compare the strength and weaknesses of different algorithms. And finally review my implementation and raise improvements.
RkJQdWJsaXNoZXIy NDk5Njg=